相关论文: Interpretable Filter Learning Using Soft Self-atte…

Transformer-based approaches have demonstrated remarkable success in various sequence-based tasks. However, traditional self-attention models may not sufficiently capture the intricate dependencies within items in sequential recommendation…

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Automatic speaker recognition algorithms typically use pre-defined filterbanks, such as Mel-Frequency and Gammatone filterbanks, for characterizing speech audio. However, it has been observed that the features extracted using these…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

This paper describes the extension and optimization of our previous work on very deep convolutional neural networks (CNNs) for effective recognition of noisy speech in the Aurora 4 task. The appropriate number of convolutional layers, the…

Speech emotion recognition (SER) is crucial for enhancing affective computing and enriching the domain of human-computer interaction. However, the main challenge in SER lies in selecting relevant feature representations from speech signals…

Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were…

Machine learning approaches to auditory object recognition are traditionally based on engineered features such as those derived from the spectrum or cepstrum. More recently, end-to-end classification systems in image and auditory…

In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition. Previous approaches of neural beamformers with multiple look directions, such as the…

Learning acoustic models directly from the raw waveform data with minimal processing is challenging. Current waveform-based models have generally used very few (~2) convolutional layers, which might be insufficient for building high-level…

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

We propose a learning-based method for the joint design of a transmit and receive filter, the constellation geometry and associated bit labeling, as well as a neural network (NN)-based detector. The method maximizes an achievable…

This paper proposes a model for transforming speech features using the frequency-directional attention model for End-to-End (E2E) automatic speech recognition. The idea is based on the hypothesis that in the phoneme system of each language,…

Speech emotion recognition is an important and challenging task in the realm of human-computer interaction. Prior work proposed a variety of models and feature sets for training a system. In this work, we conduct extensive experiments using…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Various sources have reported the WaveNet deep learning architecture being able to generate high-quality speech, but to our knowledge there haven't been studies on the interpretation or visualization of trained WaveNets. This study…

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

Convolutions operate only locally, thus failing to model global interactions. Self-attention is, however, able to learn representations that capture long-range dependencies in sequences. We propose a network architecture for audio…

Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency. One of the key ingredients is the…

Reliable transmission of 3D point clouds over wireless channels is challenging due to time-varying signal-to-noise ratio (SNR) and limited bandwidth. This paper introduces sensitivity-aware filtering and transmission (SAFT), a learned…